Conference proceeding from the First NSF/ NSA/ AFRL workshop on Secure Knowledge Management, Buff... more Conference proceeding from the First NSF/ NSA/ AFRL workshop on Secure Knowledge Management, Buffalo, NY, September 23-24, 2004
Proceedings of the Future Technologies Conference (FTC) 2018, 2018
The use of two statistical metrics in automatically identifying important keywords associated wit... more The use of two statistical metrics in automatically identifying important keywords associated with a concept such as a gene by mining scientific literature is reviewed. Starting with a subset of MEDLINE® abstracts that contain the name or synonyms of a gene in their titles, the aforementioned metrics contrast the prevalence of specific words in these documents against a broader “background set” of abstracts. If a word occurs substantially more often in the document subset associated with a gene than in the background set that acts as a reference, then the word is viewed as capturing some specific attribute of the gene.
Many Computer Science departments are moving toward C or C++ as the programming language used in ... more Many Computer Science departments are moving toward C or C++ as the programming language used in teaching the introductory computer science sequence. Some departments and many students believe that an initial introduction to C is a good idea since it allows for a smooth transition later into C ++. In this paper, some of the problems in using C as an introductory programming language are briefly reviewed, and some specific issues and solutions that are possible when C ++ is adopted are pointed out. It is concluded that while both C and C++ have their disadvantages as introductory languages, the latter would be the better choice between the two
Welcome to Kennesaw State University and the 49th annual ACM Southeast Conference, the longest co... more Welcome to Kennesaw State University and the 49th annual ACM Southeast Conference, the longest continuously-running computer-science conference. We are very pleased with this year's program, which includes internationally-known keynote speakers Dr. Marco Perez-Cisneros from the Universidad de Guadalajara, MX, and Leon Jololian of Zayed University, U.A.E. We are also fortunate to have a keynote presentation from Dr. Sue Fitzgerald of the National Science Foundation. Our program also includes eight tutorials and a student Game Design Exposition, along with peer-reviewed papers, faculty posters, and student posters. The conference program includes two special tracks or themed areas, one in Robotics and another in Digital Game Design. Each of the two themed areas generated one or more special tutorials and a special paper session.
Conference proceeding from the Fifth IASTED Conference on Computational Intelligence, August 2010... more Conference proceeding from the Fifth IASTED Conference on Computational Intelligence, August 2010, pp. 119-124. We describe two statistical metrics, Z-score and a variant of the familiar TF-IDF, which are appropriate for identifying keywords associated with genes by mining a collection of MEDLINE® abstracts. We describe experiments in clustering genes based on the identified keyword features that different genes share with each other. The quality of clustering is measured by comparing the clusters generated by a clustering algorithm against expert-defined clusters. We evaluate the quality of clustering based on keyword features identified by the two different metrics, as well as combinations of the keywords derived from the metrics. We present these results and our analysis
Abstract Abductive inference has been characterized in the AI literature as ‘inference to the bes... more Abstract Abductive inference has been characterized in the AI literature as ‘inference to the best explanation’ or as ‘plausible inference involving context-sensitive discrimination among explanatory hypotheses’. Analogously, understanding natural language involves context-sensitive discrimination among word senses, and there has been a growing awareness that it can be viewed as a type of abductive inference. Parsimonious covering theory, first formulated to model the abductive inference underlying medical diagnostic problem solving, is examined here as a method for automating natural language processing for medical expert system interfaces. The nature of ‘parsimony’ in natural language processing and the relationship of parsimonious covering to a notion of focus of attention are discussed. An experimental prototype developed to test these ideas in the context of a medical expert system is briefly described. This prototype is domain-independent in the same sense that a generic expert system shell is domain-independent. Given a knowledge base for a specific medical application, a vocabulary extractor extracts and indexes the linguistic information which it contains. In addition, an indexed domain-independent knowledge base that contains linguistic knowledge common to many domains is used. With a parsimonious covering inference mechanism superimposed on this knowledge, a natural language interface is generated for the specific application defined by the knowledge base.
Users at home and outside will be accessing the Internet increasingly from information appliances... more Users at home and outside will be accessing the Internet increasingly from information appliances such as PDAs, cell phones, and set-top boxes. These devices do not have the same rendering capabilities (display size, color depth, screen resolution, etc.) or network connectivity as traditional desktop clients, and therefore, content must be modified, or transcoded, for proper display on those devices. Advances in use of multimedia on PCs and digital telecast of television makes it necessary to have a facility available for proper transcoding of signals to make them viewable on PCs. A software solution to above problem can be much less expensive then a sole hardware solution. This paper presents a technique to web-enable such transcoders and make them available as a service for any user within the home and outside through the Internet. An example of a transcoder could be the video MPEG converter to convert MPEG2 format into MPEG1 or AVI format. 1 Introduction Traditional methods of tr...
In this paper, we briefly discuss the pedagogical issues surrounding the teaching of techniques t... more In this paper, we briefly discuss the pedagogical issues surrounding the teaching of techniques to diagnose and correct programming errors. Then we catalog several common bugs students grapple with during the course of their programming projects. We found it very valuable to document them so students can help themselves, as well as be helped by the instructor.
Analysis and classification of free text documents encompass decision-making processes that rely ... more Analysis and classification of free text documents encompass decision-making processes that rely on several clues derived from text and other contextual information. When using multiple clues, it is generally not known a priori how these should be integrated into a decision. An algorithmic sensor based on Latent Semantic Indexing (LSI) (a recent successful method for text retrieval rather than classification) is the primary sensor used in our work, but its utility is limited by the {ital reference}{ital library} of documents. Thus, there is an important need to complement or at least supplement this sensor. We have developed a system that uses a neural network to integrate the LSI-based sensor with other clues derived from the text. This approach allows for systematic fusion of several information sources in order to determine a combined best decision about the category to which a document belongs.
In this paper, we characterize assessment in terms of outcomes that indicate that the stated obje... more In this paper, we characterize assessment in terms of outcomes that indicate that the stated objectives are met, and assessment methods that measure outcomes at desired levels of performance. We consider factors such as the need for some direct measures, issues of faculty buyin, the extra cost of formal assessment, etc. We identify two assessment methods, neither of which is new, but brought together, make it practical to assess many common outcomes. The Faculty Course Assessment Report (FCAR), developed by John Estell, provides for directly assessing course outcomes, which are mapped to program outcomes. The second direct assessment method involves using an Industry Advisory Board (IAB) in evaluating capstone courses. Here, many program outcomes, including students’ employability, are assessed. We discuss why these methods are practical and desirable. We describe some implementation considerations, as well as supplementary methods. Finally, we consider the need for an integrated ap...
Many researchers believe that certain aspects of natural language processing, such as word sense ... more Many researchers believe that certain aspects of natural language processing, such as word sense disambiguation and plan recognition in stories, constitute abductive inferences. We have been working with a specific model of abduction, called parsimonious covering, applied in diagnostic problem solving, word sense disambiguation and logical form generation in some restricted settings. Diagnostic parsimonious covering has been extended into a dual-route model to account for syntactic and semantic aspects of natural language. The two routes of covering are integrated by defining “open class” linguistic concepts, aiding each other. The diagnostic model has dealt with sets, while the extended version, where syntactic considerations dictate word order, deals with sequences of linguistic concepts. Here we briefly describe the original model and the extended version, and briefly characterize the notions of covering and different criteria of parsimony. Finally we examine the question of whet...
Users at home and outside will be accessing the Internet increasingly from information appliances... more Users at home and outside will be accessing the Internet increasingly from information appliances such as PDAs, cell phones, and set-top boxes. These devices do not have the same rendering capabilities (display size, color depth, screen resolution, etc.) or network connectivity as traditional desktop clients, and therefore, content must be modified, or transcoded, for proper display on those devices. Advances
Many researchers believe that certain aspects of natural language processing, such as word sense ... more Many researchers believe that certain aspects of natural language processing, such as word sense disambiguation and plan recognition in stories, constitute abductive inferences. We have been working with a specific model of abduction, called parsimonious covering, applied in diagnostic problem solving, word sense disambiguation and logical form generation in some restricted settings. Diagnostic parsimonious covering has been extended into a dual-route model to account for syntactic and semantic aspects of natural language. The two routes of covering are integrated by defining "open class" linguistic concepts, aiding each other. The diagnostic model has dealt with sets, while the extended version, where syntactic considerations dictate word order, deals with sequences of linguistic concepts. Here we briefly describe the original model and the extended version, and briefly characterize the notions of covering and different criteria of parsimony. Finally we examine the questi...
Proceedings of the 17th International Conference on Innovations in Applied Artificial Intelligence, 2004
ABSTRACT The advent of Digital Television and the “Connected Home” has led to an information over... more ABSTRACT The advent of Digital Television and the “Connected Home” has led to an information overload to the viewer. A lot of research has been conducted towards developing interactive program guide services and products that attempt to simplify the television viewing experience. Closed captions that are part of the transmission signal of the programs aired have been identified as a good source of information [1]. Information Retrieval techniques may be applied to closed caption transcripts to create applications such as the one we describe here, called the “Similar Program Guide (SPG)”. Such a guide would notify the user of programs being aired on other channels, similar to the one he/she is currently watching or similar to the ones in the user’s profile. Additionally, this guide would allow users to compile their favorite programs and thus maintain user profiles. In this paper we discuss the approaches for development of the application. We use Information Retrieval techniques as the basis for this application.
Conference proceeding from the First NSF/ NSA/ AFRL workshop on Secure Knowledge Management, Buff... more Conference proceeding from the First NSF/ NSA/ AFRL workshop on Secure Knowledge Management, Buffalo, NY, September 23-24, 2004
Proceedings of the Future Technologies Conference (FTC) 2018, 2018
The use of two statistical metrics in automatically identifying important keywords associated wit... more The use of two statistical metrics in automatically identifying important keywords associated with a concept such as a gene by mining scientific literature is reviewed. Starting with a subset of MEDLINE® abstracts that contain the name or synonyms of a gene in their titles, the aforementioned metrics contrast the prevalence of specific words in these documents against a broader “background set” of abstracts. If a word occurs substantially more often in the document subset associated with a gene than in the background set that acts as a reference, then the word is viewed as capturing some specific attribute of the gene.
Many Computer Science departments are moving toward C or C++ as the programming language used in ... more Many Computer Science departments are moving toward C or C++ as the programming language used in teaching the introductory computer science sequence. Some departments and many students believe that an initial introduction to C is a good idea since it allows for a smooth transition later into C ++. In this paper, some of the problems in using C as an introductory programming language are briefly reviewed, and some specific issues and solutions that are possible when C ++ is adopted are pointed out. It is concluded that while both C and C++ have their disadvantages as introductory languages, the latter would be the better choice between the two
Welcome to Kennesaw State University and the 49th annual ACM Southeast Conference, the longest co... more Welcome to Kennesaw State University and the 49th annual ACM Southeast Conference, the longest continuously-running computer-science conference. We are very pleased with this year's program, which includes internationally-known keynote speakers Dr. Marco Perez-Cisneros from the Universidad de Guadalajara, MX, and Leon Jololian of Zayed University, U.A.E. We are also fortunate to have a keynote presentation from Dr. Sue Fitzgerald of the National Science Foundation. Our program also includes eight tutorials and a student Game Design Exposition, along with peer-reviewed papers, faculty posters, and student posters. The conference program includes two special tracks or themed areas, one in Robotics and another in Digital Game Design. Each of the two themed areas generated one or more special tutorials and a special paper session.
Conference proceeding from the Fifth IASTED Conference on Computational Intelligence, August 2010... more Conference proceeding from the Fifth IASTED Conference on Computational Intelligence, August 2010, pp. 119-124. We describe two statistical metrics, Z-score and a variant of the familiar TF-IDF, which are appropriate for identifying keywords associated with genes by mining a collection of MEDLINE® abstracts. We describe experiments in clustering genes based on the identified keyword features that different genes share with each other. The quality of clustering is measured by comparing the clusters generated by a clustering algorithm against expert-defined clusters. We evaluate the quality of clustering based on keyword features identified by the two different metrics, as well as combinations of the keywords derived from the metrics. We present these results and our analysis
Abstract Abductive inference has been characterized in the AI literature as ‘inference to the bes... more Abstract Abductive inference has been characterized in the AI literature as ‘inference to the best explanation’ or as ‘plausible inference involving context-sensitive discrimination among explanatory hypotheses’. Analogously, understanding natural language involves context-sensitive discrimination among word senses, and there has been a growing awareness that it can be viewed as a type of abductive inference. Parsimonious covering theory, first formulated to model the abductive inference underlying medical diagnostic problem solving, is examined here as a method for automating natural language processing for medical expert system interfaces. The nature of ‘parsimony’ in natural language processing and the relationship of parsimonious covering to a notion of focus of attention are discussed. An experimental prototype developed to test these ideas in the context of a medical expert system is briefly described. This prototype is domain-independent in the same sense that a generic expert system shell is domain-independent. Given a knowledge base for a specific medical application, a vocabulary extractor extracts and indexes the linguistic information which it contains. In addition, an indexed domain-independent knowledge base that contains linguistic knowledge common to many domains is used. With a parsimonious covering inference mechanism superimposed on this knowledge, a natural language interface is generated for the specific application defined by the knowledge base.
Users at home and outside will be accessing the Internet increasingly from information appliances... more Users at home and outside will be accessing the Internet increasingly from information appliances such as PDAs, cell phones, and set-top boxes. These devices do not have the same rendering capabilities (display size, color depth, screen resolution, etc.) or network connectivity as traditional desktop clients, and therefore, content must be modified, or transcoded, for proper display on those devices. Advances in use of multimedia on PCs and digital telecast of television makes it necessary to have a facility available for proper transcoding of signals to make them viewable on PCs. A software solution to above problem can be much less expensive then a sole hardware solution. This paper presents a technique to web-enable such transcoders and make them available as a service for any user within the home and outside through the Internet. An example of a transcoder could be the video MPEG converter to convert MPEG2 format into MPEG1 or AVI format. 1 Introduction Traditional methods of tr...
In this paper, we briefly discuss the pedagogical issues surrounding the teaching of techniques t... more In this paper, we briefly discuss the pedagogical issues surrounding the teaching of techniques to diagnose and correct programming errors. Then we catalog several common bugs students grapple with during the course of their programming projects. We found it very valuable to document them so students can help themselves, as well as be helped by the instructor.
Analysis and classification of free text documents encompass decision-making processes that rely ... more Analysis and classification of free text documents encompass decision-making processes that rely on several clues derived from text and other contextual information. When using multiple clues, it is generally not known a priori how these should be integrated into a decision. An algorithmic sensor based on Latent Semantic Indexing (LSI) (a recent successful method for text retrieval rather than classification) is the primary sensor used in our work, but its utility is limited by the {ital reference}{ital library} of documents. Thus, there is an important need to complement or at least supplement this sensor. We have developed a system that uses a neural network to integrate the LSI-based sensor with other clues derived from the text. This approach allows for systematic fusion of several information sources in order to determine a combined best decision about the category to which a document belongs.
In this paper, we characterize assessment in terms of outcomes that indicate that the stated obje... more In this paper, we characterize assessment in terms of outcomes that indicate that the stated objectives are met, and assessment methods that measure outcomes at desired levels of performance. We consider factors such as the need for some direct measures, issues of faculty buyin, the extra cost of formal assessment, etc. We identify two assessment methods, neither of which is new, but brought together, make it practical to assess many common outcomes. The Faculty Course Assessment Report (FCAR), developed by John Estell, provides for directly assessing course outcomes, which are mapped to program outcomes. The second direct assessment method involves using an Industry Advisory Board (IAB) in evaluating capstone courses. Here, many program outcomes, including students’ employability, are assessed. We discuss why these methods are practical and desirable. We describe some implementation considerations, as well as supplementary methods. Finally, we consider the need for an integrated ap...
Many researchers believe that certain aspects of natural language processing, such as word sense ... more Many researchers believe that certain aspects of natural language processing, such as word sense disambiguation and plan recognition in stories, constitute abductive inferences. We have been working with a specific model of abduction, called parsimonious covering, applied in diagnostic problem solving, word sense disambiguation and logical form generation in some restricted settings. Diagnostic parsimonious covering has been extended into a dual-route model to account for syntactic and semantic aspects of natural language. The two routes of covering are integrated by defining “open class” linguistic concepts, aiding each other. The diagnostic model has dealt with sets, while the extended version, where syntactic considerations dictate word order, deals with sequences of linguistic concepts. Here we briefly describe the original model and the extended version, and briefly characterize the notions of covering and different criteria of parsimony. Finally we examine the question of whet...
Users at home and outside will be accessing the Internet increasingly from information appliances... more Users at home and outside will be accessing the Internet increasingly from information appliances such as PDAs, cell phones, and set-top boxes. These devices do not have the same rendering capabilities (display size, color depth, screen resolution, etc.) or network connectivity as traditional desktop clients, and therefore, content must be modified, or transcoded, for proper display on those devices. Advances
Many researchers believe that certain aspects of natural language processing, such as word sense ... more Many researchers believe that certain aspects of natural language processing, such as word sense disambiguation and plan recognition in stories, constitute abductive inferences. We have been working with a specific model of abduction, called parsimonious covering, applied in diagnostic problem solving, word sense disambiguation and logical form generation in some restricted settings. Diagnostic parsimonious covering has been extended into a dual-route model to account for syntactic and semantic aspects of natural language. The two routes of covering are integrated by defining "open class" linguistic concepts, aiding each other. The diagnostic model has dealt with sets, while the extended version, where syntactic considerations dictate word order, deals with sequences of linguistic concepts. Here we briefly describe the original model and the extended version, and briefly characterize the notions of covering and different criteria of parsimony. Finally we examine the questi...
Proceedings of the 17th International Conference on Innovations in Applied Artificial Intelligence, 2004
ABSTRACT The advent of Digital Television and the “Connected Home” has led to an information over... more ABSTRACT The advent of Digital Television and the “Connected Home” has led to an information overload to the viewer. A lot of research has been conducted towards developing interactive program guide services and products that attempt to simplify the television viewing experience. Closed captions that are part of the transmission signal of the programs aired have been identified as a good source of information [1]. Information Retrieval techniques may be applied to closed caption transcripts to create applications such as the one we describe here, called the “Similar Program Guide (SPG)”. Such a guide would notify the user of programs being aired on other channels, similar to the one he/she is currently watching or similar to the ones in the user’s profile. Additionally, this guide would allow users to compile their favorite programs and thus maintain user profiles. In this paper we discuss the approaches for development of the application. We use Information Retrieval techniques as the basis for this application.
Uploads
Papers by Venu Dasigi